9 if len(arvados.current_task()['parameters']) > 0:
10 p = arvados.current_task()['parameters']
12 p = arvados.current_job()['script_parameters']
14 t = arvados.current_task().tmpdir
16 os.unlink("/usr/local/share/bcbio-nextgen/galaxy")
17 os.mkdir("/usr/local/share/bcbio-nextgen/galaxy")
18 shutil.copy("/usr/local/share/bcbio-nextgen/config/bcbio_system.yaml", "/usr/local/share/bcbio-nextgen/galaxy")
20 with open("/usr/local/share/bcbio-nextgen/galaxy/tool_data_table_conf.xml", "w") as f:
22 <!-- Locations of indexes in the BWA mapper format -->
23 <table name="bwa_indexes" comment_char="#">
24 <columns>value, dbkey, name, path</columns>
25 <file path="tool-data/bwa_index.loc" />
27 <!-- Locations of indexes in the Bowtie2 mapper format -->
28 <table name="bowtie2_indexes" comment_char="#">
29 <columns>value, dbkey, name, path</columns>
30 <file path="tool-data/bowtie2_indices.loc" />
32 <!-- Locations of indexes in the Bowtie2 mapper format for TopHat2 to use -->
33 <table name="tophat2_indexes" comment_char="#">
34 <columns>value, dbkey, name, path</columns>
35 <file path="tool-data/bowtie2_indices.loc" />
37 <!-- Location of SAMTools indexes and other files -->
38 <table name="sam_fa_indexes" comment_char="#">
39 <columns>index, value, path</columns>
40 <file path="tool-data/sam_fa_indices.loc" />
42 <!-- Location of Picard dict file and other files -->
43 <table name="picard_indexes" comment_char="#">
44 <columns>value, dbkey, name, path</columns>
45 <file path="tool-data/picard_index.loc" />
47 <!-- Location of Picard dict files valid for GATK -->
48 <table name="gatk_picard_indexes" comment_char="#">
49 <columns>value, dbkey, name, path</columns>
50 <file path="tool-data/gatk_sorted_picard_index.loc" />
55 os.mkdir("/usr/local/share/bcbio-nextgen/galaxy/tool-data")
57 with open("/usr/local/share/bcbio-nextgen/galaxy/tool-data/bowtie2_indices.loc", "w") as f:
58 f.write(subst.do_substitution(p, "GRCh37\tGRCh37\tHuman (GRCh37)\t$(dir $(bowtie2_indices))\n"))
60 with open("/usr/local/share/bcbio-nextgen/galaxy/tool-data/bwa_index.loc", "w") as f:
61 f.write(subst.do_substitution(p, "GRCh37\tGRCh37\tHuman (GRCh37)\t$(file $(bwa_index))\n"))
63 with open("/usr/local/share/bcbio-nextgen/galaxy/tool-data/gatk_sorted_picard_index.loc", "w") as f:
64 f.write(subst.do_substitution(p, "GRCh37\tGRCh37\tHuman (GRCh37)\t$(file $(gatk_sorted_picard_index))\n"))
66 with open("/usr/local/share/bcbio-nextgen/galaxy/tool-data/picard_index.loc", "w") as f:
67 f.write(subst.do_substitution(p, "GRCh37\tGRCh37\tHuman (GRCh37)\t$(file $(picard_index))\n"))
69 with open("/usr/local/share/bcbio-nextgen/galaxy/tool-data/sam_fa_indices.loc", "w") as f:
70 f.write(subst.do_substitution(p, "index\tGRCh37\t$(file $(sam_fa_indices))\n"))
72 with open("/tmp/crunch-job/gatk-variant.yaml", "w") as f:
74 # Template for whole genome Illumina variant calling with GATK pipeline
79 # to do multi-sample variant calling, assign samples the same metadata / batch
81 # batch: your-arbitrary-batch-name
84 mark_duplicates: picard
87 variantcaller: gatk-haplotype
89 quality_format: Standard
90 coverage_interval: genome
91 # for targetted projects, set the region
92 # variant_regions: /path/to/your.bed
95 os.chdir(arvados.current_task().tmpdir)
97 rcode = subprocess.call(["bcbio_nextgen.py", "--workflow", "template", "/tmp/crunch-job/gatk-variant.yaml", "project1",
98 subst.do_substitution(p, "$(file $(R1))"),
99 subst.do_substitution(p, "$(file $(R2))")])
101 os.chdir("project1/work")
103 os.symlink("/usr/local/share/bcbio-nextgen/galaxy/tool-data", "tool-data")
105 rcode = subprocess.call(["bcbio_nextgen.py", "../config/project1.yaml", "-n", os.environ['CRUNCH_NODE_SLOTS']])